arXiv research

Improved option pricing model with transaction costs.

Exponential proportion of pseudo-Anosovs in mapping class groups.

Improved averaging method for noisy observations converges strongly.

Catapult phase in neural nets shows exponential loss growth before quick decrease.

Paper proves minimal resistance for a body in a fluid with decreasing density.

Bayes optimal algorithm under certain conditions doesn't achieve exponential simple regret.

Study shows exponential error reduction in multiclass classification without bias-variance trade-off.

Introduces a new theoretical framework for exponential smoothing.

Study optimal stopping times for multi-dimensional processes with non-exponential discounting.

We consider a stochastic model of investment on an asset of a stock market for a prudent investor. She decides to buy permanent goods with a fraction $\a$ of the maximum amount of money owned in her life in order that her economic level never decreases. The optimal strategy is obtained by maximizing the exponential gro…

Decentralized Bayesian learning reduces KL-divergence exponentially.

Growth rate of the world Growth Domestic Product (GDP) is analysed to determine possible pathways of the future economic growth. The analysis is based on using the latest data of the World Bank and it reveals that the growth rate between 1960 and 2014 was following a trajectory approaching asymptotically a constant val…

This paper analyzes VAE approximation errors in conditional exponential families.

We study the global probability distribution of energy consumption per capita around the world using data from the U.S. Energy Information Administration (EIA) for 1980-2010. We find that the Lorenz curves have moved up during this time period, and the Gini coefficient G has decreased from 0.66 in 1980 to 0.55 in 2010,…

Forecasting technological progress is of great interest to engineers, policy makers, and private investors. Several models have been proposed for predicting technological improvement, but how well do these models perform? An early hypothesis made by Theodore Wright in 1936 is that cost decreases as a power law of cumul…

This research examines how the error rate of nearest neighbor classifiers varies with dataset size.

Bayesian posterior contraction rates improve with decreasing tails

New methods test discrete distributions faster with local privacy constraints.

We construct continuous-time equilibrium models based on a finite number of exponential utility investors. The investors' income rates as well as the stock's dividend rate are governed by discontinuous Levy processes. Our main result provides the equilibrium (i.e., bond and stock price dynamics) in closed-form. As an a…

Gradient descent implicitly follows regularization for general losses.

We show that every non-decreasing function $f\colon \mathbb N\to \mathbb N$ bounded from above by $a^n$ for some $a\ge 1$ can be realized (up to a natural equivalence) as the conjugacy growth function of a finitely generated group. We also construct a finitely generated group $G$ and a subgroup $H\le G$ of index 2 such…

This paper analyzes the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al, 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, Srinivas et al proved that t…

Graphical models represent multivariate and generally not normalized probability distributions. Computing the normalization factor, called the partition function, is the main inference challenge relevant to multiple statistical and optimization applications. The problem is of an exponential complexity with respect to t…

Paper proposes GEG to enhance fairness in binary and multi-class classification.

Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation is often performed by tuning the learning rate. Usual learning rate strategies are time-based i.e. monotonously decreasing. In this paper, we…

The paper studies Teichmüller TQFT for hyperbolic knots, proving exponential decay of partition functions.

Study on learning properties of scale-dependent kernels controlling stability and error.

Linear cost method approximates Gaussian Matérn processes with exponentially convergent accuracy.

We study an infinite-horizon discrete-time optimal stopping problem under non-exponential discounting. A new method, which we call the iterative approach, is developed to find subgame perfect Nash equilibria. When the discount function induces decreasing impatience, we establish the existence of an equilibrium through …

Let $Σ$ be a compact orientable surface of finite type with at least one boundary component. Let $Γ\leq \textup{Mod}(Σ)$ be a non virtually solvable subgroup. We answer a question of Lubotzky by showing that there exists a finite dimensional homological representation $ρ$ of $\textup{Mod}(Σ)$ such that $ρ(Γ)$ is not vi…

In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more data can be leveraged to reduce the required training runtime. In this paper, we…

Paper proposes a mean-field gradient descent for zero-sum games, proving convergence to Nash equilibrium.

We study the performance of a family of randomized parallel coordinate descent methods for minimizing the sum of a nonsmooth and separable convex functions. The problem class includes as a special case L1-regularized L1 regression and the minimization of the exponential loss ("AdaBoost problem"). We assume the input da…

New convergence results for NGVI with various step sizes and sample sizes.

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be reduced at the cost of reduced reliability. A training algorithm is proposed to optim…

A new algorithm detects changes in data with constant cost per iteration.

Extends ERM with exponential tilting for improved machine learning performance.

Classifies knots by lattice size, finding unknot ratios and crossing numbers.

Investment decisions shift earlier as patience decreases, with implications for pasting conditions.

Novel bounds for SGLD show generalization error decreases with more samples.

We consider the online version of the isotonic regression problem. Given a set of linearly ordered points (e.g., on the real line), the learner must predict labels sequentially at adversarially chosen positions and is evaluated by her total squared loss compared against the best isotonic (non-decreasing) function in hi…

In this paper, we construct a set of new functionals of Ricci curvature on any Kaehler manifolds which are invariant under holomorphic transfermations in Kaehler Einstein manifolds and essentially decreasing under the Kaehler Ricci flow. Moreover, if the initial metric has non-negative bisectional curvature, using Tian…

Characterizes a general range decreasing group homomorphism.

We propose a communicationally and computationally efficient algorithm for high-dimensional distributed sparse learning. At each iteration, local machines compute the gradient on local data and the master machine solves one shifted $l_1$ regularized minimization problem. The communication cost is reduced from constant …

This study investigates self-organizing dynamics in a stochastic exponential DAM model using Temporal Complexity.

Adapts SGD to noise and problem specifics for faster convergence.

TDA detects financial bubbles through early warning signals.

We investigate the waiting-time distribution of the absolute return in the Korean stock-market index KOSPI. We define the waiting time as a time interval during which the normalized absolute return remains continuously below a threshold $r_c$. Through an exponential bin plot, we observe that the waiting-time distributi…